Abstract: Provided is a mouth shape synthesis device and a method using an artificial neural network. To this end, an original video encoder that encodes original video data which is a target of a mouth shape synthesis as a video including a face of a synthesis target; an audio encoder that encodes audio data that is a basis for the mouth shape synthesis and outputs an audio embedding vector; and a synthesized video decoder that uses the original video embedding vector and the audio embedding vector as input data, and outputs synthesized video data in which a mouth shape corresponding to the audio data is synthesized on the synthesis target face may be provided.

Abstract: A coil component is provided. The coil component includes a body having fifth and sixth surfaces opposing each other, first and second surfaces respectively connecting the fifth and sixth surfaces of the body and opposing each other, and third and fourth surfaces respectively connecting the first and second surfaces of the body and opposing each other in one direction, a recess disposed in an edge between one of the first and second surfaces of the body and the sixth surface of the body, a coil portion disposed inside the body and exposed through the recess, and an external electrode including a connection portion disposed in the recess and connected to the coil portion, and a pad portion disposed on one surface of the body. A length of the pad portion in the one direction is greater than a length of the connection portion in the one direction.

Abstract: A display panel includes an amorphous silicon gate driver in which a lower voltage than the gate-off voltage output from the gate driver is applied to an adjacent stage as a low voltage transmission signal.

Abstract: A display panel includes an amorphous silicon gate driver in which a lower voltage than the gate-off voltage output from the gate driver is applied to an adjacent stage as a low voltage transmission signal.

Abstract: A display panel includes an amorphous silicon gate driver in which a lower voltage than the gate-off voltage output from the gate driver is applied to an adjacent stage as a low voltage transmission signal.

Abstract: A method for restoring a compressed image according to an embodiment of the present disclosure includes receiving monochrome image data and low resolution color image data generated from an original color image of the monochrome image data, decoding the monochrome image data and generating a low resolution monochrome image, decoding the low resolution color image data generating a low resolution color image; processing the low resolution monochrome image and generating a high resolution monochrome image in accordance with a super resolution imaging neural network; and generating a high resolution color image based on the low resolution color image and the high resolution monochrome image in accordance with a colorization imaging neural network. The imaging neural network of the present disclosure may be a deep neural network generated by machine learning, and images may be input and output in the Internet of Things environment using a 5G network.

Abstract: A method for enhancing video frame resolution according to one embodiment of the present disclosure may include loading video data including a plurality of frames having low resolution; selecting, from the group of artificial neural networks for image processing, artificial neural networks for image processing having different complexity to apply to two different frames of a video; and generating a high resolution frame by processing each frame of the video according to the selected artificial neural networks for image processing. A neural network for image processing according to one embodiment of the present disclosure may be a deep neural network generated via machine learning, and an input and output of the video may take place in an Internet of Things environment using a 5G network.

Abstract: A display panel includes an amorphous silicon gate driver in which a lower voltage than the gate-off voltage output from the gate driver is applied to an adjacent stage as a low voltage transmission signal.

Abstract: A display panel includes an amorphous silicon gate driver in which a lower voltage than the gate-off voltage output from the gate driver is applied to an adjacent stage as a low voltage transmission signal.

Abstract: A method for restoring a compressed image according to an embodiment of the present disclosure includes receiving monochrome image data and low resolution color image data generated from an original color image of the monochrome image data, decoding the monochrome image data and generating a low resolution monochrome image, decoding the low resolution color image data generating a low resolution color image; processing the low resolution monochrome image and generating a high resolution monochrome image in accordance with a super resolution imaging neural network; and generating a high resolution color image based on the low resolution color image and the high resolution monochrome image in accordance with a colorization imaging neural network. The imaging neural network of the present disclosure may be a deep neural network generated by machine learning, and images may be input and output in the Internet of Things environment using a 5G network.

Abstract: A method for enhancing the resolution of an image according to an embodiment of the present disclosure can include loading image data including a low resolution image and metadata of the image data, analyzing metadata including information related to an image processing artificial neural network to be applied to the low resolution image in the image data, selecting the image processing artificial neural network to be applied to the low resolution image from a plurality of image processing artificial neural networks, based on the metadata, and generating a high resolution image by processing the low resolution image according to the selected image processing artificial neural network. The image processing neural network of the present disclosure can be a deep neural network generated through machine learning, and the input and output of the moving image data can be performed in an Internet of Things (IoT) environment using a 5G network.

Abstract: A method for enhancing video frame resolution according to one embodiment of the present disclosure may include loading video data including a plurality of frames having low resolution; selecting, from the group of artificial neural networks for image processing, artificial neural networks for image processing having different complexity to apply to two different frames of a video; and generating a high resolution frame by processing each frame of the video according to the selected artificial neural networks for image processing. A neural network for image processing according to one embodiment of the present disclosure may be a deep neural network generated via machine learning, and an input and output of the video may take place in an Internet of Things environment using a 5G network.

Abstract: A method for enhancing image resolution according to an embodiment of the present disclosure may include receiving a low resolution image, selecting an image processing area for the low resolution image, selecting a neural network for image processing according to an attribute of the selected area among neural network groups for image processing, and generating a high resolution image for the area by processing the selected image processing area according to the selected neural network for image processing. The neural network for image processing of the present disclosure may be a deep neural network generated through machine learning, and input and output of an image may be performed in an IoT environment using a 5G network.

Abstract: A display panel includes an amorphous silicon gate driver in which a lower voltage than the gate-off voltage output from the gate driver is applied to an adjacent stage as a low voltage transmission signal.

Abstract: A display panel includes an amorphous silicon gate driver in which a lower voltage than the gate-off voltage output from the gate driver is applied to an adjacent stage as a low voltage transmission signal.

Abstract: A display panel driving apparatus includes a data processing part. The data processing part calculates a first pretilt value of previous image data to output a first pretilt signal, calculates a second pretilt value of current image data to output a second pretilt signal, analyze a luminance distribution of unit pixels from image data to output luminance distribution analysis data, analyzes a color pixel to which a pretilt is applied based on the unit pixel from the image data to output color analysis data, outputs a determination signal indicating whether the pretilt is applied to the image data, according to the luminance distribution analysis data and the color analysis data, and outputs pretilt compensation image data according to the first pretilt signal, the second pretilt signal and the determination signal, as compensation image data.

Abstract: A liquid crystal display includes a display panel including first and second subpixels, where the first subpixel includes a first switching device including a first electrode connected to the j-th data line, a second electrode connected to a first subpixel electrode and a gate electrode connected to an i-th gate line, the second subpixel includes a second switching device including a first electrode connected to a j-th data line, a second electrode connected to a second subpixel electrode and a gate electrode connected to the i-th gate line, a third switching device including a first electrode connected to the second subpixel electrode and a gate electrode connected to the i-th gate line, and a fourth switching device including a first electrode connected to the j-th data line, a second electrode connected to the first electrode of the third switching device and a gate electrode connected to the i-th gate line.

Abstract: A display panel includes an amorphous silicon gate driver in which a lower voltage than the gate-off voltage output from the gate driver is applied to an adjacent stage as a low voltage transmission signal.

Abstract: A display panel includes an amorphous silicon gate driver in which a lower voltage than the gate-off voltage output from the gate driver is applied to an adjacent stage as a low voltage transmission signal.

Abstract: A display device includes a display panel including a plurality of pixels, a power supply which supplies a common voltage and a distribution voltage to the display panel, and a timing controller which outputs a selection signal corresponding to image data input from the outside where the power supply supplies the distribution voltage having a value corresponding to the selection signal to the display panel.